Disease Surveillance by Chatbot

How Social Media Platforms Support Malaria Elimination 

By Bram Piot, Senior Surveillance and Monitoring Advisor, PSI, Kemi Tesfazghi, Mekong Malaria Elimination Technical Director, PSI and Florah Muchiri, PSI Communications Intern, Digital Health and Monitoring

Test. Treat. Track. These three words guide efforts towards malaria eliminationas well as combatting other deadly diseases. In many countries, that last steptrackingis still facilitated using traditional paper-based reporting methods or complicated digital reporting tools that makes it impossible to capture and share critical data rapidly, identify where the disease is occurring, and ultimately curb its spreadEnter social media chatbots, being used in the Greater Mekong Subregion by PSI and partners as part of our efforts to accelerate malaria elimination. 


Disease surveillance systems often lack efficient and scalable digital reporting tools to effectively respond to disease outbreaks and contain epidemics. The COVID-19 pandemic has revealed gaps in disease surveillance particularly in the private sector, which is often the first point of care for people seeking fever treatment. An estimated 65% of people in Myanmar and 77% in Laos first seek care for fever in private facilities, confirming the need to further invest in surveillance within this sector. This is particularly the case in malaria elimination settings, where standard protocols require every case to be reported within 24 hours to the local health authorities and response teams. 

Digital reporting aims to replace paper-based reporting where feasible, while making it easier and faster for health workers to report and track the spread of disease. However, digital reporting comes with its own challenges as it is generally dependent on substantial investments in training and equipment as well as the availability of functional communications infrastructure. 


In collaboration with partners such as the University of Oslo, PSI developed and successfully piloted chatbots built on popular social media platforms, such as Facebook, to support reporting malaria cases and other disease surveillance data. This tackles the issue of delays from paperbased reporting and decreases the barriers to entry presented by complicated mobile reporting tools. The chatbotallow front-line health workers — from pharmacists to doctors — to leverage a social media platform they already use on their own mobile devices, in their local language.  

PSI’s Greater Mekong Subregion Elimination of Malaria through Surveillance (GEMS) project works with private sector providers to increase access to quality malaria case managementThe project facilitates the reporting of malaria case data from the private sector into national surveillance systems in Cambodia, Laos, Myanmar, and VietnamThe GEMS chatbots for malaria case reporting are built on Facebook Messenger in Laos and Myanmar, and the locally developed and highly popular Zalo messaging platform in Vietnam. 

The chatbot in Laos was developed in 2019 using Facebook Messenger to report malaria cases confirmed through rapid diagnostic tests (RDTs)Its introduction saw the registration of 178 private sector pharmacies and clinics who can use the chatbot for reporting on essential data points such as treatment provided, referral issued, village of residence, and basic patient information. The case reports are automatically uploaded into our DHIS2 software, facilitating a much easier and faster system than the former paper-based one. Since the start of the year, this reporting mechanism has accounted for 32% of all positive malaria cases reported through the PSI network. All trained providers will be reporting their monthly summary report through the Facebook Messenger bot starting January 2020.

In Myanmar, PSI is in the process of deploying a Facebook Messenger bot for malaria case reporting within its extensive Sun Quality Health clinic network, following a successful pilot phase earlier this year. 

A similar chatbot was recently developed in Vietnam on the Zalo messaging app. Since the introduction of the chatbot in May 2020 to 67 outlets (11 clinics, 10 pharmacies, and 46 community agents), this reporting mechanism has accounted for 42% of all malaria cases seen in PSI’s GEMS+ network of private sector outlets. In addition to malaria case reporting, the chatbot was adapted to accommodate reporting of non-malarial fever cases, using a checklist of symptoms. Launched in September, the fever case reports from a network of hundreds of pharmacies and clinics are now used as an additional data source within the country’s event-based surveillance system for COVID-19. 

As of November 2020, 1,834 private sector providers (1,618 pharmacies and 216 clinics) had been trained on using the reporting mechanism. Since the launch at the end of July 2020, 431 outlets reported 1,038 customers seeking treatment for fever and/or respiratory illness.

Data collected through all of these chatbots can be sent to multiple DHIS2 instances, making it easy to share the same records with Ministries of Health and implementing partners.  While still early in the process, initial feedback from end-users indicates that the use of social media chatbots for digital reporting is feasible and offers several advantages.   


Some early lessons learned while building and deploying the chatbot include: 

  • Users like a familiar interface, local language and automated flow, which all make it easier to report data. This is particularly relevant when providers only need to report cases only occasionally. 
  • The bots do not yet remove the need for in-person case notification to local health authorities but can improve the timeliness and accuracy of case surveillance overall. 
  • End-users want options. There’s no “one size fits all” solutionwhich makes it necessary to provide them with a range of reporting tools, both digital and paper, to accommodate for all preferences. 
  • While digital reporting makes disease surveillance more timely and easier, there are still complexities inherent in supporting a surveillance system. For example, large networks of providers still require active user management by central monitoring and evaluation (M&E) teams. 
  • Training on the use of the chatbots is easy and can be done over the phone (e.g. using WhatsApp)in person by field staff or during meetings with providers. 

What’s next? 

  • End-users may require more choices than just Facebook or ZaloTherefore, PSI may develop chatbots on other social media options such as WhatsApp or Viber.  
  • As part of our efforts to strengthen overall disease surveillance, we plan to incorporate reminders for providers, and notifications to local health authorities to increase more effective usage. 
  • The bots will continue to be applied for other simple mobile data collection needs, including monthly aggregate reporting of stock levels and other key indicators. 
  • PSI will promote these bots and make them available to partners including National Malaria Programs for further strengthening of disease surveillance. 

PSI expects to see wide-scale adoption of chatbots over the next few years. The goal is to see user-friendly reporting options, as well as timely and comprehensive disease surveillance data ultimately integrated in the national Health Management Information System. The result will render outbreak detection and the response more efficient over time. 

Sign up to
Receive Updates

Donate to
Support Our Work